© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 7695
    Prev
    Next
    INDEX
    Explanations

    markers or tags indicating the start of a new section or topic in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vau
    -0.76
    sna
    -0.75
     Boyer
    -0.75
    ing
    -0.75
     Meredith
    -0.74
    Meredith
    -0.71
     Orrell
    -0.70
    pely
    -0.70
    chaikovsky
    -0.69
    ﴿
    -0.68
    POSITIVE LOGITS
     BAST
    0.88
     nonatomic
    0.87
    ERS
    0.86
    ers
    0.85
     defStyleAttr
    0.83
     newList
    0.82
     turb
    0.81
     Pinn
    0.79
     Hano
    0.79
    $",
    0.79
    Activations Density 0.129%

    No Known Activations